Using Machine Learning Analytics to Deliver Service Levels
September 21, 2016

Jerry Melnick
SIOS Technology

Share this

While the layers of abstraction created in virtualized environments afford numerous advantages, they can also obscure how the virtual resources are best allocated and how physical resources are performing. This can make maintaining optimal application performance a never-ending exercise in trial-and-error.

This post highlights some of the challenges encountered when using traditional monitoring and analytics tools, and describes how machine learning, as a next-generation analytics platform, provides a better way to meet SLAs by finding and fixing issues before they become performance problems. A future post will describe how machine learning analytics can also be used to allocate resources for optimal performance and cost-saving efficiency.

Most IT departments identify performance problems with tools that monitor a variety of discrete events against preset thresholds. For example they set a specific threshold for CPU utilization. Whenever that threshold is exceeded, the tool fires off alerts. But the use of thresholds presents several challenges. They do not account for the interrelated nature of resources in virtualized environments, where a change to or in one can have a significant impact on another. Such interrelationships exist both within and across silos. Without a complete understanding of the environment across silos, users of threshold-based tools frequently discover that their attempts to solve a problem have simply moved it to a different silo.

Thresholds often generate "alert storms" of meaningless data and miss important correlations that might indicate a severe problem exists. They are ineffective in detecting the symptoms of subtle issues that may indicate a significant imminent problem such as "noisy neighbors" or datastore latency issues. These subtle issues may not exceed a threshold related to the root cause or may exceed a threshold in short, random intervals, producing alerts that are frequently lost amid the "noise" of alert storms.

Even the so-called dynamic thresholds cannot accommodate the constant change in dynamic environments and, as a result, require significant ongoing IT intervention. And finally, while they may alert IT to an issue, they rarely provide sufficiently actionable information for resolving it. The exponential growth in the size and complexity of virtual environments has outstripped the ability of IT staff to set, manage, and continuously adjust threshold-based tools effectively. The time for an automated solution has come.

Advanced machine learning-based analytics software overcomes these and other challenges by continuously learning the many complex behaviors and interactions among interrelated objects – CPU, storage, network, applications – across the infrastructure. Unlike threshold-based solutions, this growing knowledge enables machine learning-based IT analytics solutions to provide a highly accurate means of identifying the root cause(s) of performance problems and making specific recommendations for resolving them cost-effectively.

This ability to aggregate, normalize, and then correlate and analyze hundreds of thousands of data points from different monitoring and management systems enable machine learning analytics solutions to transform massive volumes of data into meaningful insights across applications, servers and hosts, and storage and network infrastructures.

As it gathers and analyzes this wealth of data, the MLA system learns what constitutes normal behaviors, and it is this baseline that gives the system the ability to detect anomalies and find root causes automatically.

In addition to identifying root causes, advance machine learning based analytics solutions are able to simulate and predict the impact of making certain changes in resources and their allocations, which can be particularly useful for optimizing resource utilization and planning for expansion. This capability can also be useful for assessing if there is adequate capacity to handle a partial or complete failover. And these are topics worthy of a deeper dive in a future post.

Jerry Melnick is President and CEO of SIOS Technology.

Share this

The Latest

March 27, 2017

Monitoring a business means monitoring an entire business – not just IT or application performance. If businesses truly care about differentiating themselves from the competition, they must approach monitoring holistically. Separate, siloed monitoring systems are quickly becoming a thing of the past ...

March 24, 2017

A growing IT delivery gap is slowing down the majority of the businesses surveyed and directly putting revenue at risk, according to MuleSoft's 2017 Connectivity Benchmark Report on digital transformation initiatives and the business impact of APIs ...

March 23, 2017

Why containers are growing in popularity is no surprise — they’re extremely easy to spin up or down, but come with an unforeseen issue. Without the right foresight, DevOps and IT teams may lose a lot of visibility into these containers resulting in operational blind spots and even more haystacks to find the presumptive performance issue needle ...

March 22, 2017

Much emphasis is placed on servers and storage when discussing Application Performance, mainly because the application lives on a server and uses storage. However, the network has considerable importance, certainly in the case of WANs where there are ways of speeding up the transmission of data of a network ...

March 21, 2017

The majority of IT executives believe investment in IT Service Management (ITSM) is important to gain the agility needed to compete in an era of global, cross-industry disruption and digital transformation, according to Delivering Value to Today’s Digital Enterprise: The State of IT Service Management 2017, a report by BMC, conducted in association with Forbes ...

March 17, 2017

Let’s say your company has examined all the potential pros and cons, and moved your critical business applications to the cloud. The advertised benefits of the cloud seem like they’ll work out great. And in many ways, life is easier for you now. But as often happens when things seem too good to be true, reality has a way of kicking in to reveal just exactly how many things can go wrong with your cloud setup – things that can directly impact your business ...

March 16, 2017

IT leadership is more driven to be innovative than ever, but also more in need of justifying costs and showing value than ever. Combining the two is no mean feat, especially when individual technologies are put forward as the single tantalizing answer ...

March 15, 2017

The move to Citrix 7.X is in full swing. This has improved the centralizing of Management and reduction of costs, but End User Experience is becoming top of the business objectives list. However, delivering that is not something to be considered after the upgrade ...

March 14, 2017

As organizations understand the findings of the Cyber Monday Web Performance Index and look to improve their site performance for the next Cyber Monday shopping day, I wanted to offer a few recommendations to help any organization improve in 2017 ...

March 13, 2017

Online retailers stand to make a lot of money on Cyber Monday as long as their infrastructure can keep up with customers. If your company's site goes offline or substantially slows down, you're going to lose sales. And even top ecommerce sites experience performance or stability issues at peak loads, like Cyber Monday, according to Apica's Cyber Monday Web Performance Index ...